Demodulation of non-return to zero (NRZ) or other signals using multiple-input artificial intelligence/machine learning (AI/ML) model
AssigneeRaytheon Company
InventorsJacob M. Miller, H. Brown Cribbs, III
Life of this patent
Estimating the term…
Abstract
A method includes obtaining pairs of in-phase (I) and quadrature (Q) samples associated with a signal to be demodulated. The method also includes providing a set of the I/Q pairs to a trained AI/ML model. The set of the I/Q pairs includes an I/Q pair associated with a symbol being demodulated and at least one I/Q pair associated with at least one prior symbol that has been demodulated. In addition, the method includes using the trained AI/ML model to generate a symbol estimate for the symbol based on the set of the I/Q pairs, where the symbol estimate represents a portion of data that is encoded in the signal.
Claims20
A method comprising:
- obtaining pairs of in-phase (I) and quadrature (Q) samples associated with a signal to be demodulated;
- providing a set of the I/Q pairs to a trained artificial intelligence/machine learning (AI/ML) model, the set of the I/Q pairs including an I/Q pair associated with a symbol being demodulated and at least one I/Q pair associated with at least one prior symbol that has been demodulated;
- and
- using the trained AI/ML model to generate a symbol estimate for the symbol based on the set of the I/Q pairs, wherein the symbol estimate represents a portion of data that is encoded in the signal.
An apparatus comprising:
- at least one processing device configured to:
- obtain pairs of in-phase (I) and quadrature (Q) samples associated with a signal to be demodulated;
- provide a set of the I/Q pairs to a trained artificial intelligence/machine learning (AI/ML) model, the set of the I/Q pairs including an I/Q pair associated with a symbol being demodulated and at least one I/Q pair associated with at least one prior symbol that has been demodulated;
- and
- use the trained AI/ML model to generate a symbol estimate for the symbol based on the set of the I/Q pairs, wherein the symbol estimate represents a portion of data that is encoded in the signal.
A non-transitory computer readable medium containing instructions that when executed cause at least one processor to:
- obtain pairs of in-phase (I) and quadrature (Q) samples associated with a signal to be demodulated;
- provide a set of the I/Q pairs to a trained artificial intelligence/machine learning (AI/ML) model, the set of the I/Q pairs including an I/Q pair associated with a symbol being demodulated and at least one I/Q pair associated with at least one prior symbol that has been demodulated;
- and
- use the trained AI/ML model to generate a symbol estimate for the symbol based on the set of the I/Q pairs, wherein the symbol estimate represents a portion of data that is encoded in the signal.
Dependencies are inferred from the claim text.